Motion graphs

TLDR

The paper proposes a method for generating realistic, controllable motion by extracting user‑specified graph walks from motion‑capture data. It builds a directed motion graph from motion‑capture clips and transitions, then generates motion by walking the graph and selecting user‑specified walks, enabling varied locomotion styles along arbitrary paths.

Abstract

In this paper we present a novel method for creating realistic, controllable motion. Given a corpus of motion capture data, we automatically construct a directed graph called a motion graph that encapsulates connections among the database. The motion graph consists both of pieces of original motion and automatically generated transitions. Motion can be generated simply by building walks on the graph. We present a general framework for extracting particular graph walks that meet a user's specifications. We then show how this framework can be applied to the specific problem of generating different styles of locomotion along arbitrary paths.